Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering.
Yoshua BengioJean-François PaiementPascal VincentOlivier DelalleauNicolas Le RouxMarie OuimetPublished in: NIPS (2003)
Keyphrases
- spectral clustering
- multidimensional scaling
- kernel pca
- laplacian eigenmaps
- locally linear embedding
- nonlinear dimensionality reduction
- low dimensional
- manifold learning
- graph laplacian
- dimensionality reduction
- pairwise
- data clustering
- high dimensional data
- high dimensional
- feature mapping
- clustering method
- manifold learning algorithm
- cross domain
- similarity matrix
- clustering algorithm
- cluster analysis
- affinity matrix
- k means
- eigendecomposition
- image segmentation
- dimensional data
- dimension reduction
- semi supervised
- manifold structure
- constrained spectral clustering
- dimensionality reduction methods
- normalized cut
- random walk
- riemannian manifolds
- graph construction
- neighborhood graph
- subspace learning
- geodesic distance
- high dimensionality
- data points
- pattern recognition
- feature extraction